Triple
T2202049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Test Baker |
E50510
|
entity |
| Predicate | testGeometry |
P36942
|
FINISHED |
| Object | shallow underwater burst in a lagoon |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: shallow underwater burst in a lagoon | Statement: [Test Baker, testGeometry, shallow underwater burst in a lagoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testGeometry Context triple: [Test Baker, testGeometry, shallow underwater burst in a lagoon]
-
A.
hasGeometry
Indicates that an entity is associated with a specific geometric representation or spatial form.
-
B.
isGeometric
Indicates that something has the properties or form of a geometric figure, pattern, or structure.
-
C.
geometricFunction
Indicates a relationship where one entity serves as a geometric transformation or operation that, when applied, produces or modifies another geometric entity.
-
D.
relatesGeometryTo
Indicates a relationship in which one entity is associated with, defined by, or linked to a specific geometric representation or structure.
-
E.
geodesicsAre
Indicates that certain paths or curves in a space are geodesics, i.e., they locally minimize distance or follow the straightest possible trajectory according to the space’s geometry.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbfa1b41c8190b0f7467d0dcdfbcd |
completed | March 7, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69abbda706f4819094de73e1d1d1f539 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbf35c994819088a093c412931de4 |
completed | March 7, 2026, 6:01 a.m. |
Created at: March 4, 2026, 7:46 p.m.